Detecting Anomalous Swarming Agents With Graph Signal Processing

Schultz, Kevin; Saksena, Anshu; Reilly, Elizabeth P.; Hingorani, Rahul; Villafane-Delgado, Marisel

doi:10.1109/icas49788.2021.9551164

Cited by 4 publications

(4 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Such potential applications of GSP to the analysis of collective motion include filtering to denoise noisy data, graph Fourier-based clustering for unsupervised learning of both collective and individual behaviors, and estimation of global swarm states from sparse measurements. Already, we have applied the techniques from this paper to the detection of anomalous agents in an otherwise nominal swarm [61]. Beyond such concrete applications of GSP, the analysis in this work focused primarily on graph frequency in an ordinal sense, but similar investigations of other swarming behaviors may reveal power-law type trends when the frequencies are considered in an absolute sense, similar to the analysis of [53].…”

Section: Discussion and Future Directionsmentioning

confidence: 99%

Analyzing Collective Motion Using Graph Fourier Analysis

Schultz¹,

Villafane-Delgado²,

Reilly³

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

Collective motion in animal groups, such as swarms of insects, flocks of birds, and schools of fish, are some of the most visually striking examples of emergent behavior. Empirical analysis of these behaviors in experiment or computational simulation primarily involves the use of "swarm-averaged" metrics or order parameters such as velocity alignment and angular momentum. Recently, tools from computational topology have been applied to the analysis of swarms to further understand and automate the detection of fundamentally different swarm structures evolving in space and time. Here, we show how the field of graph signal processing can be used to fuse these two approaches by collectively analyzing swarm properties using graph Fourier harmonics that respect the topological structure of the swarm. This graph Fourier analysis reveals hidden structure in a number of common swarming states and forms the basis of a flexible analysis framework for collective motion.

show abstract

Section: Discussion and Future Directionsmentioning

confidence: 99%

Analyzing Collective Motion Using Graph Fourier Analysis

Schultz¹,

Villafane-Delgado²,

Reilly³

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…For example, in [14], [16], [41], the smoothness assumption of the voltages in power systems is investigated. Similarly, in [23], the smoothness of biological organisms in motion is validated empirically for a small number of samples for the application of the detection of malfunctioning or nefarious agents. However, these validations are specific to the application tested.…”

Section: B Related Workmentioning

confidence: 99%

“…For example, for the GMRF graph filter in (11) and µ µ µ = 0 in (18), we obtain h 2 0 (L) = L, which is a singular matrix. The hypothesis testing problem outlined in (23) assumes that h 0 (•), h 1 (•), L, and the statistics of the input signal are all known. This problem is equivalent to testing the structured covariance matrix of Gaussian random vectors, which has been extensively studied in the literature (see, e.g.…”

Section: A Detectors Based On a Known Modelmentioning

confidence: 99%

See 1 more Smart Citation

State Estimation in Partially Observable Power Systems via Graph Signal Processing Tools

Dabush

Kroizer

Routtenberg

2023

Sensors

View full text Add to dashboard Cite

This paper considers the problem of estimating the states in an unobservable power system, where the number of measurements is not sufficiently large for conventional state estimation. Existing methods are either based on pseudo-data that is inaccurate or depends on a large amount of data that is unavailable in current systems. This study proposes novel graph signal processing (GSP) methods to overcome the lack of information. To this end, first, the graph smoothness property of the states (i.e., voltages) is validated through empirical and theoretical analysis. Then, the regularized GSP weighted least squares (GSP-WLS) state estimator is developed by utilizing the state smoothness. In addition, a sensor placement strategy that aims to optimize the estimation performance of the GSP-WLS estimator is proposed. Simulation results on the IEEE 118-bus system show that the GSP methods reduce the estimation error magnitude by up to two orders of magnitude compared to existing methods, using only 70 sampled buses, and increase of up to 30% in the probability of bad data detection for the same probability of false alarms in unobservable systems The results conclude that the proposed methods enable an accurate state estimation, even when the system is unobservable, and significantly reduce the required measurement sensors.

show abstract

A framework for predicting scientific disruption based on graph signal processing

Yu,

Liang

2024

Information Processing & Management

View full text Add to dashboard Cite

Detecting Anomalous Swarming Agents With Graph Signal Processing

Cited by 4 publications

References 28 publications

Analyzing Collective Motion Using Graph Fourier Analysis

Analyzing Collective Motion Using Graph Fourier Analysis

State Estimation in Partially Observable Power Systems via Graph Signal Processing Tools

A framework for predicting scientific disruption based on graph signal processing

Contact Info

Product

Resources

About